add v3.

app.py

@@ -141,20 +141,15 @@ def convert_df(df):
 
 
 @st.cache_resource
-def load_GlotLID_v1(model_name, file_name):
-    model_path = hf_hub_download(repo_id=model_name, filename=file_name)
-    model = fasttext.load_model(model_path)
-    return model
-
-@st.cache_resource
-def load_GlotLID_v2(model_name, file_name):
+def load_GlotLID(model_name, file_name):
     model_path = hf_hub_download(repo_id=model_name, filename=file_name)
     model = fasttext.load_model(model_path)
     return model
 
 
-model_1 = load_GlotLID_v1(constants.MODEL_NAME, "model_v1.bin")
-model_2 = load_GlotLID_v2(constants.MODEL_NAME, "model_v2.bin")
+model_1 = load_GlotLID(constants.MODEL_NAME, "model_v1.bin")
+model_2 = load_GlotLID(constants.MODEL_NAME, "model_v2.bin")
+model_3 = load_GlotLID(constants.MODEL_NAME, "model_v3.bin")
 
 # @st.cache_resource
 def plot(label, prob):
@@ -179,7 +174,7 @@ def plot(label, prob):
     ax.set_xlabel("Confidence", color=BLACK_COLOR)
     st.pyplot(fig)
 
-def compute(sentences, version = 'v2'):
+def compute(sentences, version = 'v3'):
     """Computes the language probablities and labels for the given sentences.
 
     Args:
@@ -189,7 +184,7 @@ def compute(sentences, version = 'v2'):
         A list of language probablities and labels for the given sentences.
     """
     progress_text = "Computing Language..."
-    model_choice = model_2 if version == 'v2' else model_1
+    model_choice = model_3 if version == 'v3' else (model_2 if version == 'v2' else model_1)
     my_bar = st.progress(0, text=progress_text)
 
     probs = []
@@ -206,7 +201,7 @@ def compute(sentences, version = 'v2'):
         output_label_language = output_label.split('_')[0]
 
         # script control
-        if version in ['v2'] and output_label_language!= 'zxx':
+        if version in ['v2', 'v3'] and output_label_language!= 'zxx':
             main_script, all_scripts = get_script(sent)
             output_label_script = output_label.split('_')[1]
 
@@ -247,9 +242,9 @@ with tab1:
 
     version = st.radio(
         "Choose model",
-        ["v1", "v2"],
-        captions=["GlotLID version 1", "GlotLID version 2 (more data and languages)"],
-        index = 1,
+        ["v1", "v2", "v3"],
+        captions=["GlotLID version 1", "GlotLID version 2", "GlotLID version 3 (More languages, better quality data)"],
+        index = 2,
         key = 'version_tab1',
         horizontal = True
     )
@@ -286,9 +281,9 @@ with tab2:
 
     version = st.radio(
         "Choose model",
-        ["v1", "v2"],
-        captions=["GlotLID version 1", "GlotLID version 2 (more data and languages)"],
-        index = 1,
+        ["v1", "v2", "v3"],
+        captions=["GlotLID version 1", "GlotLID version 2", "GlotLID version 3 (More languages, better quality data)" ],
+        index = 2,
         key = 'version_tab2',
         horizontal = True
     )